Anna Koop

@[email protected]
37 Followers
32 Following
11 Posts

I'm in your talk, live-tooting it. Don't let the activity fool you, I'm listening.

Reinforcement Learning researcher, general enthusiast. Finishing PhD after exploring many alternate time streams.

Research interestsRL, AGI, lifelong learning, intelligence, comparative cognition
Personal sideCompulsive creator, enthusiastic communicator, somewhat chaotic but generally well-intentioned
AKA@annakoop, annakoop on bird site (deprecation warning)
Anna KoopNov 25, 2022
I'm looking for references for #DeepLearning, #ContinualDeepLearning, on very long timescales, specifically #LossOfPlasticity as in Rich/Shibhansh's talk here: https://www.youtube.com/watch?v=p_zknyfV9fY Anyone have any?
Maintaining Plasticity in Deep Continual Learning - Rich Sutton - CoLLAs 2022

YouTube
Show threadAnna KoopNov 16, 2022

@kongaloosh.com

Hey fellow dual-account person. But you've explicitly noted you're not using the one here.

Show threadAnna KoopNov 16, 2022

@annakoop

But I will say it's much handier finding fellow researchers when you're sitting on the same instance as them. #MastodonSetup

Anna KoopNov 16, 2022

Getting distracted with mastodon setup, so I went and made a dual account. Here for all-science, @annakoop for science and general mayhem.

Will I regret this? PROBABLY! Will I experiment anyway? ALWAYS.

DAGs are too easy, cycles are where it's at.